人工智能
计算机视觉
内窥镜
计算机科学
均方误差
数学
外科
医学
统计
作者
Jian Chen,Shuai Wang,Qingxiang Zhao,Mingcong Chen,Hongbin Liu
标识
DOI:10.1109/embc40787.2023.10340267
摘要
This work presents a novel dual-segment flexible robotic endoscope designed to enhance reachability and dexterity during ESD surgery. The proposed system is capable of executing multi-angle cutting operations at a small angle relative to the lesion surface, allowing for efficient en-bloc resection. Additionally, the system incorporates two calibrated RGB cameras and a depth estimation algorithm to provide detailed 3D information of the tumour, which is used to guide the control framework. A stereo visual servoing controller is also implemented to improve path-following performance during surgery. Experiments results indicate that the proposed system improves motion stability and precision. The root means square error (RMSE) of circle path following is 1.1991mm with a maximum of 1.4751mm. Ex-vivo testing demonstrates its significant potential for use in endoscopic surgery.
科研通智能强力驱动
Strongly Powered by AbleSci AI